Son of Zorn's lemma: Targeted style transfer using instance-aware semantic segmentation

Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is u...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 1348 - 1352
Hlavní autoři: Castillo, Carlos, Soham De, Xintong Han, Singh, Bharat, Yadav, Abhay Kumar, Goldstein, Tom
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.03.2017
Témata:
ISSN:2379-190X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only one particular object in a target image without altering the object's general morphology or surroundings. This is useful, for example, in augmented reality applications (such as the recently released Pokémon go), where one wants to alter the appearance of a single real-world object in an image frame to make it appear as a cartoon. Most notably, the rendering of real-world objects into cartoon characters has been used in a number of films and television show, such as the upcoming series Son of Zorn. We present a method for targeted style transfer that simultaneously segments and stylizes single objects selected by the user. The method uses a Markov random field model to smooth and anti-alias outlier pixels near object boundaries, so that stylized objects naturally blend into their surroundings.
AbstractList Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing derivative works of a particular artist or specific painting. This work considers targeted style transfer, in which the style of a template image is used to alter only part of a target image. For example, an artist may wish to alter the style of only one particular object in a target image without altering the object's general morphology or surroundings. This is useful, for example, in augmented reality applications (such as the recently released Pokémon go), where one wants to alter the appearance of a single real-world object in an image frame to make it appear as a cartoon. Most notably, the rendering of real-world objects into cartoon characters has been used in a number of films and television show, such as the upcoming series Son of Zorn. We present a method for targeted style transfer that simultaneously segments and stylizes single objects selected by the user. The method uses a Markov random field model to smooth and anti-alias outlier pixels near object boundaries, so that stylized objects naturally blend into their surroundings.
Author Castillo, Carlos
Goldstein, Tom
Xintong Han
Yadav, Abhay Kumar
Soham De
Singh, Bharat
Author_xml – sequence: 1
  givenname: Carlos
  surname: Castillo
  fullname: Castillo, Carlos
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
– sequence: 2
  surname: Soham De
  fullname: Soham De
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
– sequence: 3
  surname: Xintong Han
  fullname: Xintong Han
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
– sequence: 4
  givenname: Bharat
  surname: Singh
  fullname: Singh, Bharat
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
– sequence: 5
  givenname: Abhay Kumar
  surname: Yadav
  fullname: Yadav, Abhay Kumar
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
– sequence: 6
  givenname: Tom
  surname: Goldstein
  fullname: Goldstein, Tom
  organization: Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
BookMark eNotkE1Lw0AURUdRsKn-gm5m5yr1vTTJZNxJ8QsKCq0obsqb5E0ZaSYyMyL99wbs6l7O4nK4mTjzg2chZghzRNA3z8u79fp1XgCqudJVsVD1iciwAg0loqpPxWRkOkcNHxcii_ELABpVNhPxvh68HKz8HIK_jnLPfU-3ckNhx4k7GdNhzzIF8tFykD_R-Z10PibyLef0S4Fl5J58cu1Ydj37RMkN_lKcW9pHvjrmVLw93G-WT_nq5XHUXeUOVZVyw5W1BGVnulbZgpWpG8Oqq0ErsrotCluaTltkVMCgjW4AkZnqAq1tq8VUzP53HTNvv4PrKRy2xxMWf5hKVXk
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP.2017.7952376
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1509041176
9781509041176
EISSN 2379-190X
EndPage 1352
ExternalDocumentID 7952376
Genre orig-research
GroupedDBID 23M
29P
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i175t-be5ffa04dbdc7f2e7b68be7d6097af9c22f4bd9f1e170e09b98011eea621ffc53
IEDL.DBID RIE
ISICitedReferencesCount 26
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000414286201107&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:09 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i175t-be5ffa04dbdc7f2e7b68be7d6097af9c22f4bd9f1e170e09b98011eea621ffc53
PageCount 5
ParticipantIDs ieee_primary_7952376
PublicationCentury 2000
PublicationDate 2017-March
PublicationDateYYYYMMDD 2017-03-01
PublicationDate_xml – month: 03
  year: 2017
  text: 2017-March
PublicationDecade 2010
PublicationTitle Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998)
PublicationTitleAbbrev ICASSP
PublicationYear 2017
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.244413
Snippet Style transfer is an important task in which the style of a source image is mapped onto that of a target image. The method is useful for synthesizing...
SourceID ieee
SourceType Publisher
StartPage 1348
SubjectTerms Computational modeling
Convolution neural network
Feature extraction
Image color analysis
Image filtering
Image segmentation
Instance-aware semantic segmentation
Markov processes
Markov random fields
Neural networks
Semantics
Style transfer
Title Son of Zorn's lemma: Targeted style transfer using instance-aware semantic segmentation
URI https://ieeexplore.ieee.org/document/7952376
WOSCitedRecordID wos000414286201107&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA7b8KAXf2zib3IQvNitzdqm8SbDoSBjsKnDy2iSl1FYW2k7xf_eJCtTwYu3RyAE3oO87yXf9x5Cl7ryl8zn0vEDzh2fqsiJmeGIQZ_1XUmEb8e9PT_S0Siazdi4ga43WhgAsOQz6BrT_uXLXKzMU1mPssCQOJqoSSlda7U2t25E_ajuKuS5rPcwuJ1Mxoa6Rbv1tl_zU2z6GO7-7-A91PnW4eHxJsPsowZkB2jnRwvBNnqZ5BnOFX7Ni-yqxEtI0_gGTy2_GyQuq88l4MqiUyiwYbkvcGIhoQAn_ogLwCWk2r2J0MYiraVIWQc9De-mg3unHpbgJBoBVA6HQKnY9SWXgioClIcRBypDl9FYMUGI0iFhygOPuuAyznRu8gDikHhKiaB_iFpZnsERwkKDKklBZ61Yl38aQbHQd5UApZE40eE8Rm3jovnbuh_GvPbOyd_Lp2jbRMHwtgg5Q62qWME52hLvVVIWFzaIX5dtn-8
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5zCuqLPzbxt3kQfLGz7dKm8U2GY8M5Bps6fBlpchmFrZW2U_zvTbMyFXzx7QiEwB3k-y757g6hS535S0ZCaREvDC1CVWBxVmjEoMmatnQFMePennu03w_GYzaooOtVLQwAGPEZNArT_OXLRCyKp7IbyrxCxLGG1j1CXGdZrbW6dwNKgrKvkGOzm27rbjgcFOIt2ig3_pqgYgCkvfO_o3dR_bsSDw9WGLOHKhDvo-0fTQRr6GWYxDhR-DVJ46sMz2A-57d4ZBTeIHGWf84A54afQooLnfsUR4YUCrD4B08BZzDXDo6ENqbzshgprqOn9v2o1bHKcQlWpDlAboXgKcVtIkMpqHKBhn4QApW-zShXTLiu0kFhygGH2mCzkGl0cgC47zpKCa95gKpxEsMhwkLTKklB4xbXCaDmUMwnthKgNBd3dUCPUK1w0eRt2RFjUnrn-O_lC7TZGT32Jr1u_-EEbbmFKsTI4U5RNU8XcIY2xHseZem5CegXFAejLA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Son+of+Zorn%27s+lemma%3A+Targeted+style+transfer+using+instance-aware+semantic+segmentation&rft.au=Castillo%2C+Carlos&rft.au=Soham+De&rft.au=Xintong+Han&rft.au=Singh%2C+Bharat&rft.date=2017-03-01&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=1348&rft.epage=1352&rft_id=info:doi/10.1109%2FICASSP.2017.7952376&rft.externalDocID=7952376